1 code implementation • 3 Apr 2024 • Jiahao Lu, Xingyi Yang, Xinchao Wang
Foundation segmentation models, while powerful, pose a significant risk: they enable users to effortlessly extract any objects from any digital content with a single click, potentially leading to copyright infringement or malicious misuse.
no code implementations • 25 Mar 2024 • Jiacheng Deng, Jiahao Lu, Tianzhu Zhang
Unsupervised point cloud shape correspondence aims to establish point-wise correspondences between source and target point clouds.
1 code implementation • 22 Mar 2024 • Jiahao Lu, Jiacheng Deng, Tianzhu Zhang
To generate higher quality pseudo-labels and achieve more precise weakly supervised 3DIS results, we propose the Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation (BSNet), which devises a novel pseudo-labeler called Simulation-assisted Transformer.
1 code implementation • CVPR 2023 • Jiacheng Deng, Chuxin Wang, Jiahao Lu, Jianfeng He, Tianzhu Zhang, Jiyang Yu, Zhe Zhang
The key of our approach is to exploit an orientation estimation module with a domain adaptive discriminator to align the orientations of point cloud pairs, which significantly alleviates the mispredictions of symmetrical parts.
Ranked #2 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)
no code implementations • 14 Mar 2023 • Lili Bao, Jiahao Lu, Shihui Ying, Stefan Sommer
In this paper, we propose a new approach to deformable image registration that captures sliding motions.
no code implementations • ICCV 2023 • Jiahao Lu, Jiacheng Deng, Chuxin Wang, Jianfeng He, Tianzhu Zhang
Additionally, we design an affiliated transformer decoder that suppresses the interference of noise background queries and helps the foreground queries focus on instance discriminative parts to predict final segmentation results.
Ranked #3 on 3D Instance Segmentation on ScanNet(v2)
2 code implementations • 28 Oct 2022 • Jiahao Lu, CHONG YIN, Kenny Erleben, Michael Bachmann Nielsen, Sune Darkner
Recently, attempts have been made to reduce annotation requirements in feature-based self-explanatory models for lung nodule diagnosis.
2 code implementations • 27 Jun 2022 • Jiahao Lu, CHONG YIN, Oswin Krause, Kenny Erleben, Michael Bachmann Nielsen, Sune Darkner
Visualisation of the learned space further indicates that the correlation between the clustering of malignancy and nodule attributes coincides with clinical knowledge.
1 code implementation • CVPR 2022 • Jiahao Lu, Xi Sheryl Zhang, Tianli Zhao, Xiangyu He, Jian Cheng
Showing how vision Transformers are at the risk of privacy leakage via gradients, we urge the significance of designing privacy-safer Transformer models and defending schemes.
2 code implementations • 30 Mar 2021 • Jiahao Lu, Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje
We compare the performance of four Generative Adversarial Network (GAN)-based I2I translation methods and one contrastive representation learning method, subsequently combined with two representative monomodal registration methods, to judge the effectiveness of modality translation for multimodal image registration.
1 code implementation • NeurIPS 2020 • Nicolas Pielawski, Elisabeth Wetzer, Johan Öfverstedt, Jiahao Lu, Carolina Wählby, Joakim Lindblad, Nataša Sladoje
We propose contrastive coding to learn shared, dense image representations, referred to as CoMIRs (Contrastive Multimodal Image Representations).
2 code implementations • 23 Oct 2019 • Jiahao Lu, Nataša Sladoje, Christina Runow Stark, Eva Darai Ramqvist, Jan-Michaél Hirsch, Joakim Lindblad
The pipeline consists of fully convolutional regression-based nucleus detection, followed by per-cell focus selection, and CNN based classification.